Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for building and applying fuzzy term partitions, the method comprising: building a fuzzy category taxonomy; building a fuzzy term extractor based on the built fuzzy category taxonomy; associating a fuzzy term with a plurality of context data; producing a context data partition for the associated fuzzy term based on the associated plurality of context data; and applying a weight to the fuzzy term.
2. The method of claim 1 , further comprising: receiving a fuzzy term input; analyzing a usage context for the received fuzzy term input; applying a fuzzy partition value to the received fuzzy term input; applying a contextual relevancy to the received fuzzy term input; and providing an output based on the applied contextual relevancy.
This invention relates to a method for processing and refining fuzzy term inputs in a computational system, particularly for improving search accuracy and relevance in natural language processing or information retrieval applications. The method addresses the challenge of interpreting ambiguous or imprecise user inputs, such as vague search queries or incomplete commands, by dynamically adjusting their meaning based on contextual and usage data. The method begins by receiving a fuzzy term input, which may include incomplete, ambiguous, or contextually vague terms. It then analyzes the usage context of the input, which involves examining surrounding data, user history, or environmental factors to determine the most likely intended meaning. A fuzzy partition value is applied to the input, which quantifies the degree of ambiguity or uncertainty in the term. Additionally, contextual relevancy is applied, which involves weighting the input based on its relevance to the current context, such as the user's recent activities or the domain of the query. The method then generates an output based on the refined interpretation of the fuzzy term, incorporating the applied contextual relevancy and fuzzy partition value. This output may be a refined search result, a disambiguated command, or a ranked list of possible interpretations. The approach enhances the accuracy and usability of systems handling imprecise or ambiguous inputs by dynamically adapting to contextual and usage-based factors.
3. The method of claim 1 , wherein the weight applied to the fuzzy term is based on a level of expertise of a person speaking the fuzzy term or the person typing the fuzzy term.
This invention relates to natural language processing and information retrieval, specifically improving search accuracy by dynamically adjusting the weight of fuzzy terms based on the expertise level of the user. Fuzzy terms are words or phrases with ambiguous or imprecise meanings, which can lead to inaccurate search results. The method addresses this by assigning variable weights to fuzzy terms depending on whether the user is an expert or a novice. For an expert, the system may assign higher confidence to the fuzzy term, assuming greater precision in their language. For a novice, the system may reduce the weight, interpreting the term more broadly to account for potential ambiguity. The method involves analyzing user input—whether spoken or typed—to determine the expertise level, which can be inferred from factors like user history, domain knowledge, or explicit user profiles. The weighted fuzzy terms are then processed to refine search queries or improve natural language understanding in applications like chatbots, voice assistants, or document retrieval systems. This approach enhances accuracy by adapting to the user's proficiency, ensuring more relevant results for both experts and novices.
4. The method of claim 1 , wherein the context data partition is created for each fuzzy term.
A system and method for processing and analyzing text data involves partitioning context data based on fuzzy terms to improve search accuracy and relevance. The technology addresses challenges in natural language processing where exact term matching fails to capture semantic relationships or variations in user queries. By creating distinct context data partitions for each fuzzy term, the system enhances the ability to retrieve relevant information even when input queries contain slight variations, synonyms, or related concepts. The method involves identifying fuzzy terms within a text corpus, which are terms that may have multiple meanings, variations, or semantic relationships. For each fuzzy term, a dedicated context data partition is generated, storing associated contextual information such as related terms, usage patterns, and semantic relationships. This partitioning allows the system to disambiguate terms based on context, improving search results by considering broader semantic connections rather than exact matches. The system may also include preprocessing steps to normalize text data, such as stemming, lemmatization, or synonym expansion, to ensure that variations of a term are correctly mapped to the appropriate context partition. Additionally, machine learning models may be employed to refine the partitioning process by analyzing usage patterns and updating the context data partitions dynamically. By organizing context data in this manner, the system enables more accurate and context-aware information retrieval, particularly in applications such as search engines, recommendation systems, and knowledge management tools. The approach reduces ambiguity in term interpretation and enhances the relevance of retrieved results.
5. The method of claim 4 , wherein each fuzzy term has a plurality of context data partitions created for the fuzzy term and associated with the fuzzy term.
This invention relates to a system for managing fuzzy terms in a data processing environment, particularly for improving the accuracy and relevance of fuzzy term matching in databases or search systems. The problem addressed is the ambiguity and variability in how fuzzy terms (terms with imprecise or context-dependent meanings) are interpreted, leading to inaccurate search results or data retrieval. The invention involves creating multiple context data partitions for each fuzzy term. These partitions are subsets of data that provide different contextual interpretations of the fuzzy term, allowing the system to refine and disambiguate the term based on the specific context in which it is used. Each partition is associated with the fuzzy term, enabling the system to select the most relevant partition when processing queries or data entries involving the term. The method includes defining the fuzzy term, generating the context data partitions, and associating them with the term. The partitions may be based on factors such as domain-specific usage, user preferences, or historical data patterns. By storing these partitions, the system can dynamically adjust the interpretation of the fuzzy term to improve search accuracy and data retrieval performance. This approach enhances the flexibility and precision of fuzzy term processing in applications like natural language processing, database queries, and information retrieval systems.
6. The method of claim 4 , wherein the context data partition contains a set of data, and wherein the set of data is partitioned as a category, the fuzzy term, an attribute, a plurality of context data, and a crisp value.
This invention relates to data partitioning and classification within a context-aware system, addressing the challenge of efficiently organizing and retrieving structured and unstructured data based on contextual relevance. The method involves partitioning context data into distinct categories to improve data retrieval and processing accuracy. The partitioned data includes a set of categorized information, where each entry is defined by a fuzzy term, an attribute, a plurality of context data, and a crisp value. The fuzzy term represents an imprecise or subjective descriptor, while the attribute specifies a characteristic of the data. The plurality of context data provides additional contextual information, and the crisp value offers a precise, quantifiable measurement. This structured partitioning allows for more nuanced data classification, enabling systems to handle ambiguous or partially defined inputs while maintaining precise output where needed. The approach enhances decision-making in applications requiring contextual understanding, such as natural language processing, recommendation systems, and adaptive user interfaces. By integrating fuzzy and crisp data representations, the method ensures flexibility in handling real-world uncertainties while preserving the ability to derive exact values when necessary. This improves the robustness and adaptability of systems relying on contextual data analysis.
7. The method of claim 6 , wherein the crisp value is a specific value or a specific range of values that depict the fuzzy term.
This invention relates to fuzzy logic systems, specifically methods for converting fuzzy terms into crisp values. Fuzzy logic is used to handle uncertainty and imprecision in decision-making processes, but practical applications often require converting fuzzy terms into precise, actionable values. The challenge is to accurately represent fuzzy terms, which are qualitative (e.g., "high," "low," "medium"), as crisp values that can be processed by digital systems. The method involves defining a crisp value as either a specific numerical value or a specific range of values that correspond to a given fuzzy term. For example, a fuzzy term like "high temperature" might be mapped to a crisp value of 80°C or a range of 75°C to 85°C. This conversion ensures that fuzzy logic systems can interface with traditional digital systems that require precise inputs. The method may also include preprocessing steps to refine the fuzzy term before conversion, such as filtering noise or adjusting for context-specific factors. The resulting crisp value is then used in further computations or control processes, maintaining the original fuzzy logic's intent while enabling compatibility with non-fuzzy systems. This approach is particularly useful in applications like industrial automation, medical diagnostics, and control systems where both human-like reasoning and precise numerical processing are required.
8. A computer system for building and applying fuzzy term partitions, comprising: one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising: building a fuzzy category taxonomy; building a fuzzy term extractor based on the built fuzzy category taxonomy; associating a fuzzy term with a plurality of context data; producing a context data partition for the associated fuzzy term based on the associated plurality of context data; and applying a weight to the fuzzy term.
This invention relates to a computer system for building and applying fuzzy term partitions, addressing challenges in categorizing and extracting terms from unstructured data with imprecise boundaries. The system processes data using fuzzy logic to handle ambiguity, improving accuracy in term classification and extraction. The system includes processors, memory, and storage containing program instructions for executing a method. First, it constructs a fuzzy category taxonomy, which organizes terms into hierarchical categories with graded membership, allowing for partial associations rather than strict binary classifications. Next, it builds a fuzzy term extractor based on this taxonomy, enabling the system to identify and extract terms from text while accounting for contextual variations. The system then associates a fuzzy term with multiple context data points, such as surrounding text or metadata, to refine its meaning. Using this context, it generates a context data partition, grouping similar data points to enhance term relevance. Finally, the system applies a weight to the fuzzy term, adjusting its significance based on context or frequency, improving search and analysis tasks. This approach enhances natural language processing by accommodating linguistic ambiguity, making it useful for applications like document classification, information retrieval, and semantic analysis. The system dynamically adapts to varying contexts, improving term extraction accuracy in complex datasets.
9. The computer system of claim 8 , further comprising: receiving a fuzzy term input; analyzing a usage context for the received fuzzy term input; applying a fuzzy partition value to the received fuzzy term input; applying a contextual relevancy to the received fuzzy term input; and providing an output based on the applied contextual relevancy.
This invention relates to a computer system designed to process and interpret fuzzy or ambiguous terms in natural language inputs. The system addresses the challenge of handling imprecise or context-dependent language in user queries or commands, which traditional systems often struggle to interpret accurately. The system receives a fuzzy term input, such as a vague or ambiguous word or phrase, and analyzes its usage context to determine the intended meaning. It then applies a fuzzy partition value to the input, which quantifies the degree of ambiguity or uncertainty in the term. Additionally, the system applies a contextual relevancy assessment to refine the interpretation based on surrounding information or prior knowledge. Finally, the system generates an output that reflects the most relevant interpretation of the fuzzy term, taking into account both the partition value and contextual factors. This approach improves the accuracy of natural language processing by dynamically adapting to the nuances of human language, particularly in scenarios where terms lack precise definitions or vary in meaning based on context. The system may be integrated into applications such as search engines, virtual assistants, or data analysis tools to enhance their ability to understand and respond to user inputs effectively.
10. The computer system of claim 8 , wherein the weight applied to the fuzzy term is based on a level of expertise of a person speaking the fuzzy term or the person typing the fuzzy term.
This invention relates to a computer system that processes natural language input, particularly handling fuzzy or ambiguous terms. The system assigns weights to these terms based on the expertise level of the person providing the input, whether spoken or typed. The expertise level influences how the system interprets and processes the fuzzy term, improving accuracy in tasks like search, recommendation, or decision-making. The system may also adjust weights based on contextual factors such as the user's role, historical performance, or domain-specific knowledge. This approach enhances the system's ability to resolve ambiguity in user input, ensuring more precise and relevant outputs. The invention is applicable in fields like customer service, medical diagnostics, or technical support, where expertise levels vary significantly among users. By dynamically adapting to the user's expertise, the system provides tailored and contextually appropriate responses.
11. The computer system of claim 8 , wherein the context data partition is created for each fuzzy term.
A computer system is designed to process and analyze textual data by partitioning context data based on fuzzy terms. The system includes a data processing module that receives input data containing textual information and identifies fuzzy terms within the data. Fuzzy terms are words or phrases that have ambiguous or imprecise meanings, making them difficult to categorize using traditional methods. The system further includes a context data partition module that creates a separate partition for each identified fuzzy term. Each partition stores context data associated with the fuzzy term, such as surrounding text, metadata, or other relevant information that helps clarify the term's meaning in a given context. The system may also include a fuzzy term resolution module that uses the partitioned context data to resolve the ambiguity of the fuzzy term, applying natural language processing (NLP) techniques to interpret the term based on its context. The partitioned approach allows for more accurate analysis of ambiguous terms by isolating their context, improving the system's ability to understand and process textual data in applications such as search engines, document classification, or semantic analysis. The system may also include a user interface for displaying the resolved fuzzy terms and their associated context data, enabling users to review and refine the interpretations.
12. The computer system of claim 11 , wherein each fuzzy term has a plurality of context data partitions created for the fuzzy term and associated with the fuzzy term.
A computer system processes fuzzy terms by associating each term with multiple context data partitions. These partitions store contextual information relevant to the fuzzy term, enabling more precise interpretation and application of the term in different scenarios. The system dynamically adjusts the partitions based on usage patterns, improving accuracy over time. This approach addresses challenges in natural language processing where ambiguous or imprecise terms (fuzzy terms) require contextual understanding for accurate interpretation. By segmenting context data into partitions, the system enhances disambiguation and reduces errors in applications like search engines, chatbots, and decision-making algorithms. The partitions may include linguistic, domain-specific, or user-specific data, allowing the system to adapt to varying contexts. The system also supports real-time updates to partitions, ensuring relevance as new data or usage patterns emerge. This method improves the reliability of fuzzy term processing in automated systems, particularly where traditional keyword-based approaches fail to capture nuanced meanings. The invention is applicable in fields requiring high-precision language understanding, such as healthcare diagnostics, legal document analysis, and customer service automation.
13. The computer system of claim 11 , wherein the context data partition contains a set of data, and wherein the set of data is partitioned as a category, the fuzzy term, an attribute, a plurality of context data, and a crisp value.
This invention relates to a computer system for organizing and processing context data, addressing challenges in efficiently categorizing and retrieving structured information. The system partitions context data into distinct components to improve data management and analysis. The context data partition contains a structured set of data, which is organized into multiple categories. Each category includes a fuzzy term, an attribute, a plurality of context data entries, and a crisp value. The fuzzy term represents an imprecise or subjective descriptor, while the attribute defines a specific characteristic or property. The plurality of context data entries provide detailed information related to the attribute, and the crisp value offers a precise, quantifiable measurement. This structured partitioning enables more accurate data retrieval, analysis, and decision-making by clearly defining relationships between different data elements. The system enhances data processing efficiency by allowing users to quickly access relevant information based on categorized fuzzy terms and attributes, while the crisp value ensures precise measurements for analytical purposes. This approach is particularly useful in applications requiring both qualitative and quantitative data analysis, such as machine learning, natural language processing, and decision support systems.
14. The computer system of claim 13 , wherein the crisp value is a specific value or a specific range of values that depict the fuzzy term.
The invention relates to a computer system for processing fuzzy logic terms, specifically converting fuzzy terms into crisp values for precise computational use. Fuzzy logic involves handling imprecise or vague terms (e.g., "high temperature," "low pressure") in a way that mimics human reasoning. The challenge is translating these fuzzy terms into exact numerical values (crisp values) that machines can process accurately. The system includes a fuzzy logic processor that interprets fuzzy terms and maps them to specific crisp values or ranges. For example, a fuzzy term like "moderate speed" might be converted to a crisp value of 50 mph or a range between 40-60 mph. This conversion ensures that fuzzy logic-based decisions can be implemented in real-world applications, such as control systems, where precise numerical inputs are required. The system may also include a knowledge base storing predefined mappings between fuzzy terms and their corresponding crisp values, allowing for consistent and standardized interpretations. Additionally, it may feature a learning module that adapts these mappings based on new data or user feedback, improving accuracy over time. The overall goal is to bridge the gap between human-like fuzzy reasoning and machine-executable precise logic, enabling more intuitive and adaptable decision-making in automated systems.
15. A computer program product for building and applying fuzzy term partitions, comprising: one or more computer-readable storage media and program instructions stored on at least one of the one or more tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising: building a fuzzy category taxonomy; building a fuzzy term extractor based on the built fuzzy category taxonomy; associating a fuzzy term with a plurality of context data; producing a context data partition for the associated fuzzy term based on the associated plurality of context data; and applying a weight to the fuzzy term.
This invention relates to a computer program product for building and applying fuzzy term partitions, addressing challenges in categorizing and extracting terms from unstructured data with imprecise or overlapping boundaries. The system constructs a fuzzy category taxonomy, which organizes terms into hierarchical categories with graded membership, allowing for partial or uncertain classifications. A fuzzy term extractor is then built using this taxonomy to identify and extract terms from data sources, accommodating ambiguity and variability in language. Each extracted fuzzy term is associated with context data, such as surrounding text or metadata, to refine its meaning. The system partitions this context data into subsets relevant to the fuzzy term, enabling more precise term interpretation. Weights are applied to the fuzzy terms to prioritize their relevance or significance, improving information retrieval and analysis. The approach enhances natural language processing by handling ambiguity and context, making it useful for applications like search engines, document classification, and semantic analysis. The invention automates the creation of flexible term structures and their contextual application, reducing manual effort and improving accuracy in text processing tasks.
16. The computer program product of claim 15 , further comprising: receiving a fuzzy term input; analyzing a usage context for the received fuzzy term input; applying a fuzzy partition value to the received fuzzy term input; applying a contextual relevancy to the received fuzzy term input; and providing an output based on the applied contextual relevancy.
This invention relates to a computer program product for processing fuzzy terms in natural language processing (NLP) or search systems. The problem addressed is the ambiguity and variability in user inputs, particularly when terms lack precise definitions or context, leading to inaccurate search results or misinterpretations. The system receives a fuzzy term input, which is a term with multiple possible meanings or interpretations. It analyzes the usage context of the term, examining surrounding words, phrases, or user behavior to determine the intended meaning. The system then applies a fuzzy partition value, which quantifies the degree of ambiguity or membership in different possible interpretations. Additionally, it applies contextual relevancy, assessing how well each interpretation fits the current context based on predefined rules or machine learning models. Finally, the system provides an output, such as a refined search result, disambiguated term, or ranked list of possible meanings, based on the applied contextual relevancy. This approach improves the accuracy of NLP and search systems by dynamically resolving ambiguity in user inputs, ensuring more precise and relevant outputs. The system may also include preprocessing steps, such as tokenization or normalization, and may integrate with external knowledge bases or user profiles to enhance context analysis. The overall goal is to bridge the gap between imprecise user inputs and accurate system responses.
17. The computer program product of claim 15 , wherein the weight applied to the fuzzy term is based on a level of expertise of a person speaking the fuzzy term or the person typing the fuzzy term.
This invention relates to natural language processing and information retrieval systems that handle imprecise or ambiguous language terms, often referred to as "fuzzy terms." The problem addressed is the difficulty in accurately interpreting and processing such terms in search queries or spoken language, where the meaning may vary based on context, user expertise, or other factors. The solution involves dynamically adjusting the weight or significance of a fuzzy term in a query or input based on the level of expertise of the person using the term. For example, a highly technical term used by an expert may be given greater weight in a search or analysis, while the same term used by a novice may be treated with less emphasis. The system determines the user's expertise level through various means, such as historical usage patterns, user profiles, or contextual clues. This weighting mechanism improves the accuracy and relevance of search results or language processing outcomes by tailoring the interpretation of fuzzy terms to the user's knowledge level. The invention can be applied in search engines, virtual assistants, or any system requiring natural language understanding.
18. The computer program product of claim 15 , wherein the context data partition is created for each fuzzy term.
A system and method for processing natural language queries involves analyzing input text to identify fuzzy terms, which are terms with ambiguous or imprecise meanings. The system extracts context data associated with each fuzzy term to disambiguate its meaning. This context data is partitioned into separate data structures, with each partition corresponding to a specific fuzzy term. The partitions are then used to refine the interpretation of the fuzzy terms, improving the accuracy of natural language processing tasks such as search, translation, or question answering. The system may also apply machine learning techniques to analyze the context data and further enhance the disambiguation process. By organizing context data into term-specific partitions, the system ensures that relevant contextual information is readily accessible for each fuzzy term, reducing ambiguity and improving the overall performance of natural language processing applications.
19. The computer program product of claim 18 , wherein each fuzzy term has a plurality of context data partitions created for the fuzzy term and associated with the fuzzy term.
This invention relates to a computer program product for managing fuzzy terms in a data processing system, particularly for improving the accuracy and efficiency of fuzzy logic-based operations. The problem addressed is the difficulty in handling fuzzy terms, which are imprecise or subjective in nature, within computational systems that require precise data processing. The invention involves a computer program product that includes a non-transitory computer-readable storage medium with executable program code. This code is designed to create and manage multiple context data partitions for each fuzzy term. Each fuzzy term is associated with these partitions, which help in categorizing and processing the term based on different contextual scenarios. The partitions allow the system to handle variations in meaning or interpretation of the fuzzy term depending on the context in which it is used. The system further includes a processor that executes the program code to perform operations such as receiving input data containing fuzzy terms, identifying the relevant context data partitions for each term, and processing the data accordingly. This approach enhances the system's ability to interpret and utilize fuzzy terms accurately, improving decision-making processes that rely on such terms. The invention also ensures that the context data partitions are dynamically updated to reflect changes in the interpretation or usage of the fuzzy terms over time. This adaptability is crucial for maintaining the system's relevance and accuracy in real-world applications.
20. The computer program product of claim 18 , wherein the context data partition contains a set of data, and wherein the set of data is partitioned as a category, the fuzzy term, an attribute, a plurality of context data, and a crisp value.
This invention relates to a computer program product for processing context data in a structured and flexible manner. The system addresses the challenge of efficiently organizing and retrieving context data in applications where data may be ambiguous, incomplete, or subject to varying interpretations. The invention involves partitioning context data into distinct components to improve data handling and analysis. The context data partition contains a structured set of data, which is organized into specific categories. These categories include fuzzy terms, attributes, multiple context data entries, and crisp values. Fuzzy terms represent imprecise or subjective data, allowing for flexible interpretation. Attributes define characteristics or properties associated with the context data. The plurality of context data entries enables the storage of multiple related data points, while crisp values provide precise numerical or categorical data. This partitioning allows for more accurate data retrieval and processing, particularly in scenarios where data may be ambiguous or context-dependent. The system enhances data management by enabling structured yet adaptable data organization, improving decision-making in applications such as artificial intelligence, data analytics, and knowledge management.
Unknown
April 14, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.